Be part of JetBrains PHPverse 2026 on June 9 – a free online event bringing PHP devs worldwide together.

Browse all series

Leveraging AI for Laravel Development

The web development world forever changed in December, 2025. This was the month when we realized just how powerful and useful LLMs had truly become. And there's no turning back.

It's time to get on board! This train isn't stopping. Join me, as I get you up to speed in record time. Learn about Jetbrains AI, agents, prompting, vibe coding, developer-driven AI, Ralph Wiggum, and a wealth of tips and techniques to drastically speed up your workflow. Let's go!

Series trailer thumbnail

Progress

Series Info

Episodes
18
Run Time
2h 45m
Difficulty
Intermediate
Last Updated
Jan 15, 2026
Version
Latest
Play Series

Series Episodes

  1. The Basics (2)

    1. Hello, Junie. Hello, Agent.

      Let's go! We'll begin by setting up JetBrains AI within Phpstorm. We'll then use it to explore and modify the demo "Laravel Workshop" codebase. Along the way, we'll distinguish between chat and agents, we'll generate a project guidelines.md file so Junie or Claude understands our conventions.

    2. Laravel Boost is a Must

      Let's pull in the incredible Laravel Boost package to teach your AI agent how things should be done in your application. This package also includes an MCP server along with a variety of tools to expedite common actions and lookups in your codebase.
  2. Guidelines and Prompting (2)

    1. Nip it in the Bud

      My next tip for you is to "nip it in the bud." Never let AI drift away from your project's conventions. Let me show you what I mean!

    2. Prompting Essentials

      Prompting is a surprisingly big topic. But let's focus on just three prompting patterns to get you up and running.
  3. Agent Workflow (3)

    1. Vibe Coding Workshop

      Let me introduce you to vibe coding by building a peculiar little website that needs to be built. But I don't have the time to build it by hand, and I certainly don't care about the code in this case.

    2. Developer-Driven AI

      When working with AI, I prefer a more developer-driven approach. I want to work with the agent every step of the way. I design the plan, I choose the interface, and the agent works with me to implement it.

    3. Use Context7 For Up-to-Date Documentation

      LLMs often guess or fetch wildly outdated information. If I'm working with a particular version of a package or tool, I wish I could provide the agent with the most up-to-date documentation available. That's what Context7 allows for! Let me show you.
  4. Commands, Skills, Agents? (6)

    1. Claude Commands Explained

      Think of a command as a trigger: "do this thing." If you'd like a parallel to Laravel, the closest equivalent is an Artisan command. However, of course, Claude commands are not code. They're Markdown files!

    2. PhpStorm Prompt Library

      Next up, I'll show you how to use PhpStorm's prompt library to upgrade a component from the Vue 2 Options API to the Vue 3 Composition API with TypeScript. We'll create a custom prompt and run it on any file selection.

    3. Claude Skills Explained

      Claude skills are like field guides for your codebase. They're your way of telling the agent, "This is how we handle things in these parts!"

    4. Laravel's Code Simplifier Agent

      Taylor Otwell recently made a port of the popular code simplifier agent, but optimized for Laravel development. Let's pull it in, and give it a go.

    5. Claude Subagents Explained

      Commands, skills, subagents? It gets confusing pretty quickly! Let's make it clear by building a subagent that runs in isolation so that it doesn't clog up your main context window.

    6. Let Your Agent Use Chrome

      Have you ever asked an agent to perform a bit of work, it completes it, and then you test it out in the browser: blank screen! If only your agent could visit the page itself to confirm that things are functioning properly. Hmm...
  5. Developer Workflow (5)

    1. Ask AI to Edit a GitHub PR

      Wouldn't it be neat if we could @mention AI and request that it make changes to a PR...even from our phones? Well, you can! It's easy.

    2. Get the Plan Right. Seriously.

      After endless mistakes, I've learned that it's essential that you get the plan just right before you unleash the agent on your codebase. Go back and forth multiple times. Have it interview you. Get it right!

    3. The Debate is Over. Testing is a Must.

      There was a time, long ago, when developers couldn't decide on the value of tests. Are they necessary, or are they a waste of time. Well - that debate is over. If you're leveraging AI agents, a full test suite is a requirement. You have to do it.

    4. Worktrees, Agents, Peas, and Carrots

      Git worktrees allow your agents to work on multiple tasks simultaneously without creating collisions in your code. Each agent gets its own workspace.

    5. The Ralph Wiggum Technique Explained

      This next technique I'm about to share with you...is wild! A definition won't do. You need to see this in action.

Continue Learning

The Ralph Wiggum Technique thumbnail

The Ralph Wiggum Technique

With Sabatino Masala
Launching May 18, 2026

Join me as I perform a deep-dive into the agentic looping technique known as "Ralph Wiggum." In this series, we’re not just building a script, we’re building the surrounding system that makes an agent reliable enough to collaborate with. We’ll work through permissions, sandbox rules, hooks, and safer ways to run in more autonomous modes. By the end, we’ll have something much bigger than a typical demo: a working approach for spec-driven agent development that can run locally, in the background, or on a remote machine over SSH. Let's go!

  • 16 Episodes
So You Want to Build an Agent thumbnail

So You Want to Build an Agent

With Jeffrey Way

You're likely using an AI agent every day at this point, but do you truly understand how it works under the hood? What separates an agent from a general chat? What's a tool? How do we provide the loop for executing these tools? In this series, we'll demystify some of these concepts by building a basic agent that is capable of interacting with your file system and triggering tools.

  • 9 Episodes
The Batteries-Included AI Toolkit thumbnail

The Batteries-Included AI Toolkit

With Jeremy McPeak

The Laravel AI SDK is a first-party toolkit for adding AI features to your applications. Using a helpdesk app as our playground, you’ll learn structured output, chat with memory, streaming, tool use, retrieval, and everything else you need to build AI features that are reliable, testable, and ready for production. This is an incredibly powerful toolkit, and I can't wait to show you what you can build. Let's get going!

  • 13 Episodes
Watch Me AI the UI thumbnail

Watch Me AI the UI

With Jeffrey Way

In this workshop, come along as I upgrade the visual design of our Laracasts team dashboard. As you'll see, design work can sometimes be a bit tricky to orchestrate. Can AI properly evaluate a screenshot and convert it to CSS? Well, yes...and no! But luckily, we have a variety of techniques we can use to increase our odds of success. Let's go!

  • 5 Episodes
AI Developer Workflows thumbnail

AI Developer Workflows

With Jeffrey Way

It's a brand new world. Suddenly, we find ourselves less writing code line by line, and more writing plans, coordinating agents, and building workflows. There's a lot to learn. But we gotcha!In this series, each episode will demonstrate one potential AI workflow that you might adopt in your own projects. Check back often, as we'll be adding new episodes every month.

  • 3 Episodes